{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GQOTS5VHPGZT3HZP7AJFVTMAOO","short_pith_number":"pith:GQOTS5VH","schema_version":"1.0","canonical_sha256":"341d3976a779b33d9f2ff8125acd8073a0b48c134decaa309504ad33d45ce2e6","source":{"kind":"arxiv","id":"2605.23556","version":1},"attestation_state":"computed","paper":{"title":"Is Dimensionality a Barrier for Retrieval Models?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","math.CO"],"primary_cat":"cs.LG","authors_text":"Guy Bresler, Jonathan Kogan, Kiril Bangachev, Yury Polyanskiy","submitted_at":"2026-05-22T12:22:20Z","abstract_excerpt":"Why does the low dimensionality of representations, typically $d\\approx 1000$, not prevent modern embedding-based retrieval models from scaling to billions, or even trillions, of data points? To answer this question, we study maximal-margin embeddings in the following retrieval model, classically studied in communication complexity [PS86] and more recently in embedding-based retrieval [WBNL26]. Let $A\\in \\{0,1\\}^{N\\times n}$ be a matrix indicating whether each of $N$ queries is relevant to each of $n$ documents. We are interested in the largest margin $m>0,$ denoted by $\\mathsf{m}^{\\mathsf{rd}"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.23556","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T12:22:20Z","cross_cats_sorted":["cs.IR","math.CO"],"title_canon_sha256":"4b4741a4338f2c1218079c5591d0251608310f6ee02f2653bb7b53213f69d761","abstract_canon_sha256":"4b1b787a32b27925bc4964020222e8325041f7b5ea320cc08b4035118227b5db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:02:00.777048Z","signature_b64":"Z9EDxgqCeJ3K3NqbDQa1PZIwCHdernTSA+0IW3/+D6E8WZ4vhvmIi7u2x7R4szQW8f3Qm65xRPCEWdyLH8DNAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"341d3976a779b33d9f2ff8125acd8073a0b48c134decaa309504ad33d45ce2e6","last_reissued_at":"2026-05-25T02:02:00.776273Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:02:00.776273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is Dimensionality a Barrier for Retrieval Models?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","math.CO"],"primary_cat":"cs.LG","authors_text":"Guy Bresler, Jonathan Kogan, Kiril Bangachev, Yury Polyanskiy","submitted_at":"2026-05-22T12:22:20Z","abstract_excerpt":"Why does the low dimensionality of representations, typically $d\\approx 1000$, not prevent modern embedding-based retrieval models from scaling to billions, or even trillions, of data points? To answer this question, we study maximal-margin embeddings in the following retrieval model, classically studied in communication complexity [PS86] and more recently in embedding-based retrieval [WBNL26]. Let $A\\in \\{0,1\\}^{N\\times n}$ be a matrix indicating whether each of $N$ queries is relevant to each of $n$ documents. We are interested in the largest margin $m>0,$ denoted by $\\mathsf{m}^{\\mathsf{rd}"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23556","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.23556/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.23556","created_at":"2026-05-25T02:02:00.776409+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.23556v1","created_at":"2026-05-25T02:02:00.776409+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23556","created_at":"2026-05-25T02:02:00.776409+00:00"},{"alias_kind":"pith_short_12","alias_value":"GQOTS5VHPGZT","created_at":"2026-05-25T02:02:00.776409+00:00"},{"alias_kind":"pith_short_16","alias_value":"GQOTS5VHPGZT3HZP","created_at":"2026-05-25T02:02:00.776409+00:00"},{"alias_kind":"pith_short_8","alias_value":"GQOTS5VH","created_at":"2026-05-25T02:02:00.776409+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GQOTS5VHPGZT3HZP7AJFVTMAOO","json":"https://pith.science/pith/GQOTS5VHPGZT3HZP7AJFVTMAOO.json","graph_json":"https://pith.science/api/pith-number/GQOTS5VHPGZT3HZP7AJFVTMAOO/graph.json","events_json":"https://pith.science/api/pith-number/GQOTS5VHPGZT3HZP7AJFVTMAOO/events.json","paper":"https://pith.science/paper/GQOTS5VH"},"agent_actions":{"view_html":"https://pith.science/pith/GQOTS5VHPGZT3HZP7AJFVTMAOO","download_json":"https://pith.science/pith/GQOTS5VHPGZT3HZP7AJFVTMAOO.json","view_paper":"https://pith.science/paper/GQOTS5VH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.23556&json=true","fetch_graph":"https://pith.science/api/pith-number/GQOTS5VHPGZT3HZP7AJFVTMAOO/graph.json","fetch_events":"https://pith.science/api/pith-number/GQOTS5VHPGZT3HZP7AJFVTMAOO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GQOTS5VHPGZT3HZP7AJFVTMAOO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GQOTS5VHPGZT3HZP7AJFVTMAOO/action/storage_attestation","attest_author":"https://pith.science/pith/GQOTS5VHPGZT3HZP7AJFVTMAOO/action/author_attestation","sign_citation":"https://pith.science/pith/GQOTS5VHPGZT3HZP7AJFVTMAOO/action/citation_signature","submit_replication":"https://pith.science/pith/GQOTS5VHPGZT3HZP7AJFVTMAOO/action/replication_record"}},"created_at":"2026-05-25T02:02:00.776409+00:00","updated_at":"2026-05-25T02:02:00.776409+00:00"}